{"id":"https://openalex.org/W3106772683","doi":"https://doi.org/10.14778/3425879.3425881","title":"Jointly optimizing preprocessing and inference for DNN-based visual analytics","display_name":"Jointly optimizing preprocessing and inference for DNN-based visual analytics","publication_year":2020,"publication_date":"2020-10-01","ids":{"openalex":"https://openalex.org/W3106772683","doi":"https://doi.org/10.14778/3425879.3425881","mag":"3106772683"},"language":"en","primary_location":{"id":"doi:10.14778/3425879.3425881","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3425879.3425881","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072348548","display_name":"Daniel Kang","orcid":"https://orcid.org/0000-0001-9860-9938"},"institutions":[{"id":"https://openalex.org/I4210109743","display_name":"DAWN Center for Independent Living","ror":"https://ror.org/01dwm7q20","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210109743"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Daniel Kang","raw_affiliation_strings":["Stanford DAWN Project"],"affiliations":[{"raw_affiliation_string":"Stanford DAWN Project","institution_ids":["https://openalex.org/I4210109743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035083818","display_name":"Ankit Mathur","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109743","display_name":"DAWN Center for Independent Living","ror":"https://ror.org/01dwm7q20","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210109743"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ankit Mathur","raw_affiliation_strings":["Stanford DAWN Project"],"affiliations":[{"raw_affiliation_string":"Stanford DAWN Project","institution_ids":["https://openalex.org/I4210109743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066947967","display_name":"Teja Veeramacheneni","orcid":null},"institutions":[{"id":"https://openalex.org/I4210109743","display_name":"DAWN Center for Independent Living","ror":"https://ror.org/01dwm7q20","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210109743"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Teja Veeramacheneni","raw_affiliation_strings":["Stanford DAWN Project"],"affiliations":[{"raw_affiliation_string":"Stanford DAWN Project","institution_ids":["https://openalex.org/I4210109743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002538469","display_name":"Peter Bailis","orcid":"https://orcid.org/0000-0003-1166-7823"},"institutions":[{"id":"https://openalex.org/I4210109743","display_name":"DAWN Center for Independent Living","ror":"https://ror.org/01dwm7q20","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210109743"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Peter Bailis","raw_affiliation_strings":["Stanford DAWN Project"],"affiliations":[{"raw_affiliation_string":"Stanford DAWN Project","institution_ids":["https://openalex.org/I4210109743"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5005554337","display_name":"Matei Zaharia","orcid":"https://orcid.org/0000-0002-7547-7204"},"institutions":[{"id":"https://openalex.org/I4210109743","display_name":"DAWN Center for Independent Living","ror":"https://ror.org/01dwm7q20","country_code":"US","type":"nonprofit","lineage":["https://openalex.org/I4210109743"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matei Zaharia","raw_affiliation_strings":["Stanford DAWN Project"],"affiliations":[{"raw_affiliation_string":"Stanford DAWN Project","institution_ids":["https://openalex.org/I4210109743"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5072348548"],"corresponding_institution_ids":["https://openalex.org/I4210109743"],"apc_list":null,"apc_paid":null,"fwci":2.2471,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.9017443,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"14","issue":"2","first_page":"87","last_page":"100"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9995999932289124,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8726916313171387},{"id":"https://openalex.org/keywords/bottleneck","display_name":"Bottleneck","score":0.8567942380905151},{"id":"https://openalex.org/keywords/visual-analytics","display_name":"Visual analytics","score":0.7019148468971252},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6795324683189392},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.5728403925895691},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5640989542007446},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5350860953330994},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40374523401260376},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.38090986013412476},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.37485843896865845},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3671005368232727},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36505138874053955},{"id":"https://openalex.org/keywords/real-time-computing","display_name":"Real-time computing","score":0.34067219495773315},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3350233733654022},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.25211527943611145},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.1381770670413971}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8726916313171387},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.8567942380905151},{"id":"https://openalex.org/C59732488","wikidata":"https://www.wikidata.org/wiki/Q2528440","display_name":"Visual analytics","level":3,"score":0.7019148468971252},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6795324683189392},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.5728403925895691},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5640989542007446},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5350860953330994},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40374523401260376},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.38090986013412476},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.37485843896865845},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3671005368232727},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36505138874053955},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.34067219495773315},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3350233733654022},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.25211527943611145},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.1381770670413971},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14778/3425879.3425881","is_oa":false,"landing_page_url":"https://doi.org/10.14778/3425879.3425881","pdf_url":null,"source":{"id":"https://openalex.org/S4210226185","display_name":"Proceedings of the VLDB Endowment","issn_l":"2150-8097","issn":["2150-8097"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the VLDB Endowment","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":61,"referenced_works":["https://openalex.org/W1797268635","https://openalex.org/W1821462560","https://openalex.org/W2009832130","https://openalex.org/W2044535169","https://openalex.org/W2108598243","https://openalex.org/W2117696986","https://openalex.org/W2119144962","https://openalex.org/W2125203716","https://openalex.org/W2140196014","https://openalex.org/W2140199336","https://openalex.org/W2146395539","https://openalex.org/W2193145675","https://openalex.org/W2194775991","https://openalex.org/W2285660444","https://openalex.org/W2286256158","https://openalex.org/W2368124317","https://openalex.org/W2420699360","https://openalex.org/W2442974303","https://openalex.org/W2466675884","https://openalex.org/W2508602506","https://openalex.org/W2513554817","https://openalex.org/W2516141709","https://openalex.org/W2540279855","https://openalex.org/W2541839172","https://openalex.org/W2549139847","https://openalex.org/W2556889869","https://openalex.org/W2563587242","https://openalex.org/W2599379624","https://openalex.org/W2599765304","https://openalex.org/W2604445072","https://openalex.org/W2625457103","https://openalex.org/W2626696598","https://openalex.org/W2752236330","https://openalex.org/W2765234579","https://openalex.org/W2786278116","https://openalex.org/W2803764703","https://openalex.org/W2804032941","https://openalex.org/W2805214778","https://openalex.org/W2883929540","https://openalex.org/W2899771611","https://openalex.org/W2912981821","https://openalex.org/W2913260599","https://openalex.org/W2946920775","https://openalex.org/W2946948417","https://openalex.org/W2950656546","https://openalex.org/W2953212265","https://openalex.org/W2963510045","https://openalex.org/W2963893493","https://openalex.org/W2979245724","https://openalex.org/W2997828269","https://openalex.org/W3000318171","https://openalex.org/W3004171485","https://openalex.org/W3015151524","https://openalex.org/W3016892718","https://openalex.org/W3045321348","https://openalex.org/W3082972076","https://openalex.org/W3103272053","https://openalex.org/W3103442520","https://openalex.org/W3106250896","https://openalex.org/W4236868170","https://openalex.org/W4242495425"],"related_works":["https://openalex.org/W1657880117","https://openalex.org/W2595172197","https://openalex.org/W2127970246","https://openalex.org/W2084856301","https://openalex.org/W1001352512","https://openalex.org/W3182718252","https://openalex.org/W4210310791","https://openalex.org/W2062940763","https://openalex.org/W2937343495","https://openalex.org/W4360833258"],"abstract_inverted_index":{"While":[0],"deep":[1],"neural":[2],"networks":[3],"(DNNs)":[4],"are":[5],"an":[6,20],"increasingly":[7],"popular":[8],"way":[9],"to":[10,34,41,195],"query":[11],"large":[12],"corpora":[13],"of":[14,23,72,93,109],"data,":[15],"their":[16],"significant":[17],"runtime":[18,126,134],"remains":[19],"active":[21],"area":[22],"research.":[24],"As":[25],"a":[26,63,125,155,176,201],"result,":[27],"researchers":[28],"have":[29],"proposed":[30],"systems":[31,58,85],"and":[32,45,112,140,157,160,165,180],"optimizations":[33,98,174,191],"reduce":[35],"these":[36,173],"costs":[37],"by":[38,115],"allowing":[39],"users":[40],"trade":[42],"off":[43],"accuracy":[44,111,203],"speed.":[46],"In":[47],"this":[48],"work,":[49],"we":[50,67,95,105,123],"examine":[51],"end-to-end":[52,100,197],"DNN":[53,131,141],"execution":[54,142],"in":[55,81,154,175,207],"visual":[56,83,101,120,130,185,208],"analytics":[57,84,102],"on":[59,86,149,183],"modern":[60,87],"accelerators.":[61],"Through":[62],"novel":[64,107,177],"measurement":[65],"study,":[66],"show":[68,188],"that":[69,189],"the":[70,79,91,150],"preprocessing":[71,139,147],"data":[73],"(e.g.,":[74],"decoding,":[75],"resizing)":[76],"can":[77,192],"be":[78],"bottleneck":[80,92],"many":[82],"hardware.":[88],"To":[89],"address":[90],"preprocessing,":[94],"introduce":[96,106],"two":[97],"for":[99,128,143,167],"systems.":[103],"First,":[104],"methods":[108],"achieving":[110],"throughput":[113,169,198],"trade-offs":[114],"using":[116],"natively":[117],"present,":[118],"low-resolution":[119],"data.":[121],"Second,":[122],"develop":[124],"engine":[127,135],"efficient":[129],"inference.":[132],"This":[133],"a)":[136],"efficiently":[137,162],"pipelines":[138],"inference,":[144],"b)":[145],"places":[146],"operations":[148],"CPU":[151],"or":[152],"GPU":[153],"hardware-":[156],"input-aware":[158],"manner,":[159],"c)":[161],"manages":[163],"memory":[164],"threading":[166],"high":[168],"execution.":[170],"We":[171,187],"implement":[172],"system,":[178],"Smol,":[179],"evaluate":[181],"Smol":[182],"eight":[184],"datasets.":[186],"its":[190],"achieve":[193],"up":[194],"5.9X":[196],"improvements":[199],"at":[200],"fixed":[202],"over":[204],"recent":[205],"work":[206],"analytics.":[209]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":8},{"year":2020,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}